Handle the switch to/from the hypervisor/software timer when a vCPU is
blocking in common x86 instead of in VMX.  Even though VMX is the only
user of a hypervisor timer, the logic and all functions involved are
generic x86 (unless future CPUs do something completely different and
implement a hypervisor timer that runs regardless of mode).

Handling the switch in common x86 will allow for the elimination of the
pre/post_blocks hooks, and also lets KVM switch back to the hypervisor
timer if and only if it was in use (without additional params).  Add a
comment explaining why the switch cannot be deferred to kvm_sched_out()
or kvm_vcpu_block().

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20211208015236.1616697-8-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Move the seemingly generic block_vcpu_list from kvm_vcpu to vcpu_vmx, and
rename the list and all associated variables to clarify that it tracks
the set of vCPU that need to be poked on a posted interrupt to the wakeup
vector.  The list is not used to track _all_ vCPUs that are blocking, and
the term "blocked" can be misleading as it may refer to a blocking
condition in the host or the guest, where as the PI wakeup case is
specifically for the vCPUs that are actively blocking from within the
guest.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20211208015236.1616697-7-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Remove kvm_vcpu.pre_pcpu as it no longer has any users.  No functional
change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20211208015236.1616697-6-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Move the posted interrupt pre/post_block logic into vcpu_put/load
respectively, using the kvm_vcpu_is_blocking() to determining whether or
not the wakeup handler needs to be set (and unset).  This avoids updating
the PI descriptor if halt-polling is successful, reduces the number of
touchpoints for updating the descriptor, and eliminates the confusing
behavior of intentionally leaving a "stale" PI.NDST when a blocking vCPU
is scheduled back in after preemption.

The downside is that KVM will do the PID update twice if the vCPU is
preempted after prepare_to_rcuwait() but before schedule(), but that's a
rare case (and non-existent on !PREEMPT kernels).

The notable wart is the need to send a self-IPI on the wakeup vector if
an outstanding notification is pending after configuring the wakeup
vector.  Ideally, KVM would just do a kvm_vcpu_wake_up() in this case,
but the scheduler doesn't support waking a task from its preemption
notifier callback, i.e. while the task is right in the middle of
being scheduled out.

Note, setting the wakeup vector before halt-polling is not necessary:
once the pending IRQ will be recorded in the PIR, kvm_vcpu_has_events()
will detect this (via kvm_cpu_get_interrupt(), kvm_apic_get_interrupt(),
apic_has_interrupt_for_ppr() and finally vmx_sync_pir_to_irr()) and
terminate the polling.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20211208015236.1616697-5-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Bring in fix for VT-d posted interrupts before further changing the code in 5.17.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Avoid warnings on s390 like
[ 1801.980931] CPU: 12 PID: 117600 Comm: kworker/12:0 Tainted: G            E     5.17.0-20220113.rc0.git0.32ce2abb03cf.300.fc35.s390x+next #1
[ 1801.980938] Workqueue: events irqfd_inject [kvm]
[...]
[ 1801.981057] Call Trace:
[ 1801.981060]  [<000003ff805f0f5c>] mark_page_dirty_in_slot+0xa4/0xb0 [kvm]
[ 1801.981083]  [<000003ff8060e9fe>] adapter_indicators_set+0xde/0x268 [kvm]
[ 1801.981104]  [<000003ff80613c24>] set_adapter_int+0x64/0xd8 [kvm]
[ 1801.981124]  [<000003ff805fb9aa>] kvm_set_irq+0xc2/0x130 [kvm]
[ 1801.981144]  [<000003ff805f8d86>] irqfd_inject+0x76/0xa0 [kvm]
[ 1801.981164]  [<0000000175e56906>] process_one_work+0x1fe/0x470
[ 1801.981173]  [<0000000175e570a4>] worker_thread+0x64/0x498
[ 1801.981176]  [<0000000175e5ef2c>] kthread+0x10c/0x110
[ 1801.981180]  [<0000000175de73c8>] __ret_from_fork+0x40/0x58
[ 1801.981185]  [<000000017698440a>] ret_from_fork+0xa/0x40

when writing to a guest from an irqfd worker as long as we do not have
the dirty ring.

Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Reluctantly-acked-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20220113122924.740496-1-borntraeger@linux.ibm.com>
Fixes: 2efd61a6

 ("KVM: Warn if mark_page_dirty() is called without an active vCPU")
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Add a VMX specific test to verify that KVM doesn't explode if userspace
attempts KVM_RUN when emulation is required with a pending exception.
KVM VMX's emulation support for !unrestricted_guest punts exceptions to
userspace instead of attempting to synthesize the exception with all the
correct state (and stack switching, etc...).

Punting is acceptable as there's never been a request to support
injecting exceptions when emulating due to invalid state, but KVM has
historically assumed that userspace will do the right thing and either
clear the exception or kill the guest.  Deliberately do the opposite and
attempt to re-enter the guest with a pending exception and emulation
required to verify KVM continues to punt the combination to userspace,
e.g. doesn't explode, WARN, etc...

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211228232437.1875318-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Reject KVM_RUN if emulation is required (because VMX is running without
unrestricted guest) and an exception is pending, as KVM doesn't support
emulating exceptions except when emulating real mode via vm86.  The vCPU
is hosed either way, but letting KVM_RUN proceed triggers a WARN due to
the impossible condition.  Alternatively, the WARN could be removed, but
then userspace and/or KVM bugs would result in the vCPU silently running
in a bad state, which isn't very friendly to users.

Originally, the bug was hit by syzkaller with a nested guest as that
doesn't require kvm_intel.unrestricted_guest=0.  That particular flavor
is likely fixed by commit cd0e615c ("KVM: nVMX: Synthesize
TRIPLE_FAULT for L2 if emulation is required"), but it's trivial to
trigger the WARN with a non-nested guest, and userspace can likely force
bad state via ioctls() for a nested guest as well.

Checking for the impossible condition needs to be deferred until KVM_RUN
because KVM can't force specific ordering between ioctls.  E.g. clearing
exception.pending in KVM_SET_SREGS doesn't prevent userspace from setting
it in KVM_SET_VCPU_EVENTS, and disallowing KVM_SET_VCPU_EVENTS with
emulation_required would prevent userspace from queuing an exception and
then stuffing sregs.  Note, if KVM were to try and detect/prevent the
condition prior to KVM_RUN, handle_invalid_guest_state() and/or
handle_emulation_failure() would need to be modified to clear the pending
exception prior to exiting to userspace.

 ------------[ cut here ]------------
 WARNING: CPU: 6 PID: 137812 at arch/x86/kvm/vmx/vmx.c:1623 vmx_queue_exception+0x14f/0x160 [kvm_intel]
 CPU: 6 PID: 137812 Comm: vmx_invalid_nes Not tainted 5.15.2-7cc36c3e

-pop #279
 Hardware name: ASUS Q87M-E/Q87M-E, BIOS 1102 03/03/2014
 RIP: 0010:vmx_queue_exception+0x14f/0x160 [kvm_intel]
 Code: <0f> 0b e9 fd fe ff ff 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00
 RSP: 0018:ffffa45c83577d38 EFLAGS: 00010202
 RAX: 0000000000000003 RBX: 0000000080000006 RCX: 0000000000000006
 RDX: 0000000000000000 RSI: 0000000000010002 RDI: ffff9916af734000
 RBP: ffff9916af734000 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000006
 R13: 0000000000000000 R14: ffff9916af734038 R15: 0000000000000000
 FS:  00007f1e1a47c740(0000) GS:ffff99188fb80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f1e1a6a8008 CR3: 000000026f83b005 CR4: 00000000001726e0
 Call Trace:
  kvm_arch_vcpu_ioctl_run+0x13a2/0x1f20 [kvm]
  kvm_vcpu_ioctl+0x279/0x690 [kvm]
  __x64_sys_ioctl+0x83/0xb0
  do_syscall_64+0x3b/0xc0
  entry_SYSCALL_64_after_hwframe+0x44/0xae

Reported-by:  <syzbot+82112403ace4cbd780d8@syzkaller.appspotmail.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211228232437.1875318-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Verify that the PMU event filter works as expected.

Note that the virtual PMU doesn't work as expected on AMD Zen CPUs (an
intercepted rdmsr is counted as a retired branch instruction), but the
PMU event filter does work.

Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20220115052431.447232-7-jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Extract the x86 model number from CPUID.01H:EAX.

Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20220115052431.447232-6-jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Move this static inline function to processor.h, so that it can be
used in individual tests, as needed.

Opportunistically replace the bare 'unsigned' with 'unsigned int.'

Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20220115052431.447232-5-jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Replace the one ad hoc "AuthenticAMD" CPUID vendor string comparison
with a new function, is_amd_cpu().

Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20220115052431.447232-4-jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Refactor is_intel_cpu() to make it easier to reuse the bulk of the
code for other vendors in the future.

Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20220115052431.447232-3-jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

The PMU event filter may contain up to 300 events. Replace the linear
search in reprogram_gp_counter() with a binary search.

Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20220115052431.447232-2-jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

vm_xsave_req_perm() is currently defined and used by x86_64 only.
Make it compiled into vm_create_with_vcpus() only when on x86_64
machines. Otherwise, it would cause linkage errors, e.g. on s390x.

Fixes: 415a3c33

 ("kvm: selftests: Add support for KVM_CAP_XSAVE2")
Reported-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Tested-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Message-Id: <20220118014817.30910-1-wei.w.wang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

According to Intel extended feature disable (XFD) spec, the sub-function i
(i > 1) of CPUID function 0DH enumerates "details for state component i.
ECX[2] enumerates support for XFD support for this state component."

If KVM does not report F(XFD) feature (e.g. due to CONFIG_X86_64),
then the corresponding XFD support for any state component i
should also be removed. Translate this dependency into KVM terms.

Fixes: 690a757d

 ("kvm: x86: Add CPUID support for Intel AMX")
Signed-off-by: Like Xu <likexu@tencent.com>
Message-Id: <20220117074531.76925-1-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Rewrite the comment in kvm_mmu_slot_remove_write_access() that explains
why it is safe to flush TLBs outside of the MMU lock after
write-protecting SPTEs for dirty logging. The current comment is a long
run-on sentence that was difficult to understand. In addition it was
specific to the shadow MMU (mentioning mmu_spte_update()) when the TDP
MMU has to handle this as well.

The new comment explains:
 - Why the TLB flush is necessary at all.
 - Why it is desirable to do the TLB flush outside of the MMU lock.
 - Why it is safe to do the TLB flush outside of the MMU lock.

No functional change intended.

Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20220113233020.3986005-5-dmatlack@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

SPTEs are tagged with software-only bits to indicate if it is
"MMU-writable" and "Host-writable". These bits are used to determine why
KVM has marked an SPTE as read-only.

Document these bits and their invariants, and enforce the invariants
with new WARNs in spte_can_locklessly_be_made_writable() to ensure they
are not accidentally violated in the future.

Opportunistically move DEFAULT_SPTE_{MMU,HOST}_WRITABLE next to
EPT_SPTE_{MMU,HOST}_WRITABLE since the new documentation applies to
both.

No functional change intended.

Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20220113233020.3986005-4-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

When handling the changed_pte notifier and the new PTE is read-only,
clear both the Host-writable and MMU-writable bits in the SPTE. This
preserves the invariant that MMU-writable is set if-and-only-if
Host-writable is set.

No functional change intended. Nothing currently relies on the
aforementioned invariant and technically the changed_pte notifier is
dead code.

Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20220113233020.3986005-3-dmatlack@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

When the TDP MMU is write-protection GFNs for page table protection (as
opposed to for dirty logging, or due to the HVA not being writable), it
checks if the SPTE is already write-protected and if so skips modifying
the SPTE and the TLB flush.

This behavior is incorrect because it fails to check if the SPTE
is write-protected for page table protection, i.e. fails to check
that MMU-writable is '0'.  If the SPTE was write-protected for dirty
logging but not page table protection, the SPTE could locklessly be made
writable, and vCPUs could still be running with writable mappings cached
in their TLB.

Fix this by only skipping setting the SPTE if the SPTE is already
write-protected *and* MMU-writable is already clear.  Technically,
checking only MMU-writable would suffice; a SPTE cannot be writable
without MMU-writable being set.  But check both to be paranoid and
because it arguably yields more readable code.

Fixes: 46044f72

 ("kvm: x86/mmu: Support write protection for nesting in tdp MMU")
Cc: stable@vger.kernel.org
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20220113233020.3986005-2-dmatlack@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

blocked_vcpu_on_cpu_lock is taken from hard interrupt context
(pi_wakeup_handler), therefore it cannot sleep.

Switch it to a raw spinlock.

Fixes:

[41297.066254] BUG: scheduling while atomic: CPU 0/KVM/635218/0x00010001
[41297.066323] Preemption disabled at:
[41297.066324] [<ffffffff902ee47f>] irq_enter_rcu+0xf/0x60
[41297.066339] Call Trace:
[41297.066342]  <IRQ>
[41297.066346]  dump_stack_lvl+0x34/0x44
[41297.066353]  ? irq_enter_rcu+0xf/0x60
[41297.066356]  __schedule_bug.cold+0x7d/0x8b
[41297.066361]  __schedule+0x439/0x5b0
[41297.066365]  ? task_blocks_on_rt_mutex.constprop.0.isra.0+0x1b0/0x440
[41297.066369]  schedule_rtlock+0x1e/0x40
[41297.066371]  rtlock_slowlock_locked+0xf1/0x260
[41297.066374]  rt_spin_lock+0x3b/0x60
[41297.066378]  pi_wakeup_handler+0x31/0x90 [kvm_intel]
[41297.066388]  sysvec_kvm_posted_intr_wakeup_ipi+0x9d/0xd0
[41297.066392]  </IRQ>
[41297.066392]  asm_sysvec_kvm_posted_intr_wakeup_ipi+0x12/0x20
...

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

The new module parameter to control PMU virtualization should apply
to Intel as well as AMD, for situations where userspace is not trusted.
If the module parameter allows PMU virtualization, there could be a
new KVM_CAP or guest CPUID bits whereby userspace can enable/disable
PMU virtualization on a per-VM basis.

If the module parameter does not allow PMU virtualization, there
should be no userspace override, since we have no precedent for
authorizing that kind of override. If it's false, other counter-based
profiling features (such as LBR including the associated CPUID bits
if any) will not be exposed.

Change its name from "pmu" to "enable_pmu" as we have temporary
variables with the same name in our code like "struct kvm_pmu *pmu".

Fixes: b1d66dad

 ("KVM: x86/svm: Add module param to control PMU virtualization")
Suggested-by : Jim Mattson <jmattson@google.com>
Signed-off-by: Like Xu <likexu@tencent.com>
Message-Id: <20220111073823.21885-1-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

KVM forbids KVM_SET_CPUID2 after KVM_RUN was performed on a vCPU unless
the supplied CPUID data is equal to what was previously set. Test this.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20220117150542.2176196-5-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

In preparation to reusing the existing 'get_cpuid_test' for testing
"KVM_SET_CPUID{,2} after KVM_RUN" rename it to 'cpuid_test' to avoid
the confusion.

No functional change intended.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20220117150542.2176196-4-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Commit feb627e8

 ("KVM: x86: Forbid KVM_SET_CPUID{,2} after KVM_RUN")
forbade changing CPUID altogether but unfortunately this is not fully
compatible with existing VMMs. In particular, QEMU reuses vCPU fds for
CPU hotplug after unplug and it calls KVM_SET_CPUID2. Instead of full ban,
check whether the supplied CPUID data is equal to what was previously set.

Reported-by: Igor Mammedov <imammedo@redhat.com>
Fixes: feb627e8

 ("KVM: x86: Forbid KVM_SET_CPUID{,2} after KVM_RUN")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20220117150542.2176196-3-vkuznets@redhat.com>
Cc: stable@vger.kernel.org
[Do not call kvm_find_cpuid_entry repeatedly. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

kvm_update_cpuid_runtime() mangles CPUID data coming from userspace
VMM after updating 'vcpu->arch.cpuid_entries', this makes it
impossible to compare an update with what was previously
supplied. Introduce __kvm_update_cpuid_runtime() version which can be
used to tweak the input before it goes to 'vcpu->arch.cpuid_entries'
so the upcoming update check can compare tweaked data.

No functional change intended.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20220117150542.2176196-2-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

According to CPUID 0x0A.EBX bit vector, the event [7] should be the
unrealized event "Topdown Slots" instead of the *kernel* generalized
common hardware event "REF_CPU_CYCLES", so we need to skip the cpuid
unavaliblity check in the intel_pmc_perf_hw_id() for the last
REF_CPU_CYCLES event and update the confusing comment.

If the event is marked as unavailable in the Intel guest CPUID
0AH.EBX leaf, we need to avoid any perf_event creation, whether
it's a gp or fixed counter. To distinguish whether it is a rejected
event or an event that needs to be programmed with PERF_TYPE_RAW type,
a new special returned value of "PERF_COUNT_HW_MAX + 1" is introduced.

Fixes: 62079d8a

 ("KVM: PMU: add proper support for fixed counter 2")
Signed-off-by: Like Xu <likexu@tencent.com>
Message-Id: <20220105051509.69437-1-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Fix sparse warnings in xstate and remove inline prefix.

Fixes: 980fe2fd

 ("x86/fpu: Extend fpu_xstate_prctl() with guest permissions")
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Message-Id: <20220113180825.322333-1-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

This selftest covers two aspects of AMX.  The first is triggering #NM
exception and checking the MSR XFD_ERR value.  The second case is
loading tile config and tile data into guest registers and trapping to
the host side for a complete save/load of the guest state.  TMM0
is also checked against memory data after save/restore.

Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20211223145322.2914028-4-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Those changes can avoid dereferencing pointer compile issue
when amx_test.c reference state->xsave.

Move struct kvm_x86_state definition to processor.h.

Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20211223145322.2914028-3-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

For AMX support it is recommended to load XCR0 after XFD, so
that KVM does not see XFD=0, XCR=1 for a save state that will
eventually be disabled (which would lead to premature allocation
of the space required for that save state).

It is also required to load XSAVE data after XCR0 and XFD, so
that KVM can trigger allocation of the extra space required to
store AMX state.

Adjust vcpu_load_state to obey these new requirements.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20211223145322.2914028-2-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Always intercepting IA32_XFD causes non-negligible overhead when this
register is updated frequently in the guest.

Disable r/w emulation after intercepting the first WRMSR(IA32_XFD)
with a non-zero value.

Disable WRMSR emulation implies that IA32_XFD becomes out-of-sync
with the software states in fpstate and the per-cpu xfd cache. This
leads to two additional changes accordingly:

  - Call fpu_sync_guest_vmexit_xfd_state() after vm-exit to bring
    software states back in-sync with the MSR, before handle_exit_irqoff()
    is called.

  - Always trap #NM once write interception is disabled for IA32_XFD.
    The #NM exception is rare if the guest doesn't use dynamic
    features. Otherwise, there is at most one exception per guest
    task given a dynamic feature.

p.s. We have confirmed that SDM is being revised to say that
when setting IA32_XFD[18] the AMX register state is not guaranteed
to be preserved. This clarification avoids adding mess for a creative
guest which sets IA32_XFD[18]=1 before saving active AMX state to
its own storage.

Signed-off-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220105123532.12586-22-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

KVM can disable the write emulation for the XFD MSR when the vCPU's fpstate
is already correctly sized to reduce the overhead.

When write emulation is disabled the XFD MSR state after a VMEXIT is
unknown and therefore not in sync with the software states in fpstate and
the per CPU XFD cache.

Provide fpu_sync_guest_vmexit_xfd_state() which has to be invoked after a
VMEXIT before enabling interrupts when write emulation is disabled for the
XFD MSR.

It could be invoked unconditionally even when write emulation is enabled
for the price of a pointless MSR read.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220105123532.12586-21-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

When KVM_CAP_XSAVE2 is supported, userspace is expected to allocate
buffer for KVM_GET_XSAVE2 and KVM_SET_XSAVE using the size returned
by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2).

Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Guang Zeng <guang.zeng@intel.com>
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220105123532.12586-20-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

With KVM_CAP_XSAVE, userspace uses a hardcoded 4KB buffer to get/set
xstate data from/to KVM. This doesn't work when dynamic xfeatures
(e.g. AMX) are exposed to the guest as they require a larger buffer
size.

Introduce a new capability (KVM_CAP_XSAVE2). Userspace VMM gets the
required xstate buffer size via KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2).
KVM_SET_XSAVE is extended to work with both legacy and new capabilities
by doing properly-sized memdup_user() based on the guest fpu container.
KVM_GET_XSAVE is kept for backward-compatible reason. Instead,
KVM_GET_XSAVE2 is introduced under KVM_CAP_XSAVE2 as the preferred
interface for getting xstate buffer (4KB or larger size) from KVM
(Link: https://lkml.org/lkml/2021/12/15/510

)

Also, update the api doc with the new KVM_GET_XSAVE2 ioctl.

Signed-off-by: Guang Zeng <guang.zeng@intel.com>
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220105123532.12586-19-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Userspace needs to inquire KVM about the buffer size to work
with the new KVM_SET_XSAVE and KVM_GET_XSAVE2. Add the size info
to guest_fpu for KVM to access.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220105123532.12586-18-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Extend CPUID emulation to support XFD, AMX_TILE, AMX_INT8 and
AMX_BF16. Adding those bits into kvm_cpu_caps finally activates all
previous logics in this series.

Hide XFD on 32bit host kernels. Otherwise it leads to a weird situation
where KVM tells userspace to migrate MSR_IA32_XFD and then rejects
attempts to read/write the MSR.

Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220105123532.12586-17-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Two XCR0 bits are defined for AMX to support XSAVE mechanism. Bit 17
is for tilecfg and bit 18 is for tiledata.

The value of XCR0[17:18] is always either 00b or 11b. Also, SDM
recommends that only 64-bit operating systems enable Intel AMX by
setting XCR0[18:17]. 32-bit host kernel never sets the tile bits in
vcpu->arch.guest_supported_xcr0.

Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220105123532.12586-16-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

This saves one unnecessary VM-exit in guest #NM handler, given that the
MSR is already restored with the guest value before the guest is resumed.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220105123532.12586-15-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Emulate read/write to IA32_XFD_ERR MSR.

Only the saved value in the guest_fpu container is touched in the
emulation handler. Actual MSR update is handled right before entering
the guest (with preemption disabled)

Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Zeng Guang <guang.zeng@intel.com>
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220105123532.12586-14-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>